blog-all
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined topic parameters and passes them to downstream publishing skills. This creates an attack surface where instructions embedded within the topic strings could potentially influence the behavior of the sub-skills.
- Ingestion points: User-supplied parameters in the
/blog-allcommand (SKILL.md). - Boundary markers: The skill does not specify delimiters or "ignore" instructions for the interpolated topic data.
- Capability inventory: The skill coordinates three separate blog publishing skills that perform automated content generation and deployment (SKILL.md).
- Sanitization: No sanitization or validation of the input strings is described.
- [PROMPT_INJECTION]: The skill includes instructions to "Run fully autonomously" and to "not ask for confirmation between sites." These instructions direct the agent to skip human review checkpoints during a multi-step execution process involving external publication, reducing user oversight of the agent's actions.
Audit Metadata